© JUL 2021 | IRE Journals | Volume 5 Issue 1 | ISSN: 2456-8880

Chat Bot Using AWS

GOWTHAM S1, HARISH R2, ILAYA BHARATHI M3, BIJI ROSE4
1, 2, 3
Information Technology, Dr N. G. P Institute of Technology
4
Assistant Professor, Dr N.G.P Institute of Technology

Abstract- This E-Booking with chat bot project is an related to previous output. This project mainly focuses
Artificial Intelligence based web application on enabling chat-bot to become a search engine that
designed to aid the car rental company to enable can process the next search with the relation to the
renting of cars. It has a user-friendly interface which previous search output. In chat-bot context, this
helps the user to communicate with our bot and rent functionality will enhance the capability of chat-bot’s
them for specific period. Communication can be input processing.
done by chatting or by means of speaking. The ability
of a bot to understand human language as it is 1.1 WHAT IS A chat-bot
spoken was done with N L P (Natural Language A chat-bot is a computer program that simulates
Processing). The categories of rental cars will be human conversation through voice commands or text
provided while speaking with our bot. Based on the chats or both. chat-bot, short for chatterbot, is an
type of car required by the customer, the user shall Artificial Intelligence (AI) feature that can be
be able to make bookings. The bot shall also check embedded and used through any major messaging
for the availability of the car and rent the car to the applications. There are a number of synonyms for
customer. This bot shall ask the user about some chat-bot, including "talkbot," "bot," "IM bot,"
important information such as date and time of "interactive agent" or "artificial conversation entity."
journey, type of car etc. Also, it will need an
identification number. Using these details, the tool 1.2 CHAT-BOT IN USE
shall help the customer to book a car for the journey. A chat-bot is an automated program that interacts with
It can also keep the information of number of customers like a human would and cost little to
bookings in current month or in last 6 month or in nothing to engage with. chat-bots attend to customers
last year. This helps them to track company business at all times of the day and week and are not limited by
and their earning in any month or in any year. Based time or a physical location. This makes its
on this information they can take decision regarding implementation appealing to a lot of businesses that
their business development. It also provides another may not have the manpower or financial resources to
feature that the admin can manually chat with their keep employees working around the clock.
customers in case of any technical difficulties. It also
acts as a bridge for both customers and the company. A chat-bot works in a couple of ways: set guidelines
It saves both time and labor. The main advantage is and Machine Learning. A chat-bot that functions with
that the user shall be able to choose a car depending a set of guidelines in place is limited in its
on his budget. conversation. It can only respond to a set number of
requests and vocabulary and is only as intelligent as its
I. INTRODUCTION programming code. An example of a limited bot is an
automated banking bot that asks the caller some
Artificial intelligence chat-bot is a technology that questions to understand what the caller wants to be
makes interactions between man and machines using done. The bot would make a command like “Please tell
natural language possible. From literature, we found me what I can do for you by saying account balances,
out that in general, chat-bot are functions like a typical account transfer, or bill payment.” If the customer
search engine. Although chat-bot just produced only responds with "credit card balance," the bot would not
one output instead of multiple outputs/results, the understand the request and would proceed to either
basic process flow is the same where each time an repeat the command or transfer the caller to a human
input is entered, the new search will be done. Nothing assistant.

IRE 1702863 ICONIC RESEARCH AND ENGINEERING JOURNALS 264

 © JUL 2021 | IRE Journals | Volume 5 Issue 1 | ISSN: 2456-8880

1.3 SUCCESS RATE OF CHAT-BOTS ON 1.7 CUSTOMER ORIENTED PROGRESSION

WEBSITES The call center approach of staying bounded with the
The digitalization of all the industries has scattered its consumers has been arched whilst a few years. The
sweep establishing a rostrum where innovation has emphasis on customer experiences and rendering
become the essence of development. Analogous to that towards a differential hem when in strife to excel
is the rise of chat-bots, which is becoming a vibrant amongst the intense competition has led to the rise of
option to deal with customer service and is in the chat-bots. Cost-effective, and user-friendly as prime
process of elaborating its functions to increase characteristics chat-bots serve the end user as the first
efficiency. It is profoundly definite from the recent point of contact with the reduced hassle and a much-
study done by Gartner that chat-bots would be in simplified process.
charge of managing 85% of all the customer
interactions by 2020. This evolution has happened II. HARDWARE SPECIFICATION
about in various stages. The hatch of this technology
initiated as early as 1950 with Alan Turing’s The Hardware specification is made simple from basic
intelligent machine which was then succeeded by mobile users to advance computer system users. The
another intelligent machine that could establish a most basic hardware specification required for running
quality interface between a machine and a human, this application is a mobile phone or a computer
making it more tangible. The graph did not show a system with browser which support javascript.
steep until now, attributing its presence to the
increasing demand for customer-oriented processes The user can remotely use the web portal or the
and competition. software in order to request about their car rental. The
proposed system is implemented for the car rental
1.4 THE UPSWING IN THE USE OF communication in specified premises only. It can be
MESSAGING APPLICATIONS extended to state level or national level. Other
The preferred channel of communication is what the bookings such as hotel reservation also can be
messaging applications have transformed into. The included in this project.
number of people getting connected through these
platforms is amplifying rapidly. chat-bots operate on 2.1 SOFTWARE SPECIFICATION
an identical methodology which contains enormous Operating System: Windows, Linux or Mac.
prospective for market penetration. Server/DB: Amazon Lex.
Front End: CSS, JAVASCRIPT, JQuery.
1.5 AUGMENTING SERVICES OF Back End: Amazon cloud services.
CONVERSATIONAL INTERFACES
Facebook’s annual developer conference has bolstered 2.2 SOFTWARE DESCRIPTION
the need for technologies that whirl to establish more 2.3.1 AMAZON WEB SERVICES
human-like dialogues and discourse. The superior
level of chat-bots that is illustrated by ‘Siri’ and Amazon Web Services (AWS), the cloud platform
‘Cortana’ are the versions that demonstrate the offered by Amazon.com Inc , has become a giant
dialogue discourse in the voice form. component of the e-commerce giant's business
portfolio. Having grown steadily in the 30-percent
1.6 PROPELLING GROWTH OF ARTIFICIAL range the past few quarters, AWS is a frontrunner to
INTELLIGENCE other cloud computing platforms such as competitor
The statistics of AI market that blankets all the major Microsoft Azure. AWS can be broken into three main
technologies such as Machine learning, Image products: EC2, Amazon’s virtual machine service,
recognition, and speech processing are predicted to hit Glacier, a low-cost cloud storage service, and S3,
a mark of $5.05 billion by 2020 as per the studies Amazon’s storage system. AWS is so large and
released by Statista. present in the computing world that it's far outpaced
its competitors. As of February 2020, one independent
analyst

IRE 1702863 ICONIC RESEARCH AND ENGINEERING JOURNALS 265

 © JUL 2021 | IRE Journals | Volume 5 Issue 1 | ISSN: 2456-8880

1. Easy to use:
Amazon Lex provides an easy-to-use console to guide
you through the process of creating your own chat-bot
in minutes, building conversational interfaces into
your applications. You supply just a few example
phrases and Amazon Lex builds a complete natural
language model through which your user can interact
using voice and text, to ask questions, get answers, and
reports AWS has over a third of the market at 32.4%, complete sophisticated tasks.
with Azure following behind at half that amount
17.6%, and Google Cloud at 6%. 2. Seamlessly deploy and scale:
With Amazon Lex, you can build, test, and deploy
your chat-bots directly from the Amazon Lex console.
Amazon Lex enables you to easily publish your voice
or text chat-bots to mobile devices, web apps, and chat
services such as Facebook Messenger, Slack, and
Twilio SMS. Once published, your Amazon Lex bot
processes voice or text input in conversation with your
end-users. Amazon Lex is a fully managed service so
as your user engagement increases, you don’t need to
worry about provisioning hardware and managing
infrastructure to power your bot experience.

3. Built in integration with aws:

Amazon Lex provides built-in integration with AWS
2.3.2 AMAZON LEX
Lambda, AWS MobileHub and Amazon CloudWatch
and you can easily integrate with many other services
Amazon Lex is a service for building conversational
on the AWS platform including Amazon Cognito, and
interfaces into any application using voice and text.
Amazon DynamoDB. You can take advantage of the
Amazon Lex’s high-quality speech recognition and
power of the AWS platform for security, monitoring,
natural language understanding capabilities make it
user authentication, business logic, storage and mobile
possible to build powerful interfaces to applications.
app development.
You can add a voice or text chat interface to create bots
on mobile devices that can help customers with many
4. Cost effective:
basic tasks, such as accessing their bank account,
With Amazon Lex, there are no upfront costs or
booking tickets, ordering food, or calling a cab.
minimum fees. You are only charged for the text or
Amazon Lex integrates with ‘Amazon Cognito’ so you
speech requests that are made. Amazon Lex pay-as-
can control user management, authentication, and sync
you-go pricing and low cost per request make it a cost
across all devices. Here we are excited about utilizing
effective way to build conversational interfaces
evolving speech recognition and natural language
anywhere. With the Amazon Lex free tier. You can
processing technology to enhance the lives of
easily try Amazon Lex without any investment.
customers. In our project Amazon Lex represents a
great opportunity to deliver a better service to
customers at the right time and in the right place
through Chat Bot with the help of ‘Amazon Web
Service’ Cloud System.

• Benefits of using Amazon Lex

IRE 1702863 ICONIC RESEARCH AND ENGINEERING JOURNALS 266

 © JUL 2021 | IRE Journals | Volume 5 Issue 1 | ISSN: 2456-8880

Node.js being designed without threads doesn't mean

you can't take advantage of multiple cores in your
environment. Child processes can be spawned by
using our child_process.fork() API, and are designed
to be easy to communicate with. Built upon that same
interface is the cluster module, which allows you to
share sockets between processes to enable load
balancing over your cores.

III. FUNCTIONAL DESIGN

Functional Design is a paradigm used to simplify the

design of hardware and software devices such as
computer software and increasingly,3D models. A
functional design assures that each modular part of a
device has only one responsibilities and performs that
responsibility with the minimum of side effects on
other parts. Functionally designed modules tend to
have low coupling.
2.3.3 NODE JS
The standard way to assure functional design is to
As an asynchronous event-driven JavaScript runtime, review the description of a module. If the description
Node.js is build scalable network applications. In the includes conjunctions such as “and” or “or”, then the
following "hello world" example, many connections design has more than one responsibility and is
can be handled concurrently. Upon each connection, therefore likely to have side effects. The
the callback is fired, but if there is no work to be done, responsibilities need to be divided into several
Node.js will sleep. modules in order to achieve a functional design.

Node.js is similar in design to, and influenced by, IV. INTEGRATING BOT WITH OUR WEB
systems like Ruby's Event Machine and Python's APPLICATION
Twisted. Node.js takes the event model a bit further. It
presents an event loop as a runtime construct instead After configuring lambda function with our bot, we
of as a library. In other systems, there is always a could integrate our bot in our concerned web
blocking call to start the event-loop. Typically, application. We have created a website called
behavior is defined through callbacks at the beginning Kommunicate.io . In the back end we have a done a
of a script, and at the end a server is started through a coding part we could easily integrate our bot. It just
blocking call like EventMachine::run(). In Node.js, normally asks Access Id(This will be provided by
there is no such start-the-event-loop call. Node.js amazon while purchasing amazon cloud services),
simply enters the event loop after executing the input Secret access key(This will be provided while creating
script. Node.js exits the event loop when there are no a bot in amazon lex), Region( This is a server where
more callbacks to perform. This behavior is like we developed our bot), Name of the bot in amazon lex,
browser JavaScript — the event loop is hidden from alias name. After completing this form we can directly
the user. integrate our bot profile. This is a step where our bot
gets deployed in our web application.
HTTP is a first-class citizen in Node.js, designed with
streaming and low latency in mind. This makes
Node.js well suited for the foundation of a web library
or framework.

IRE 1702863 ICONIC RESEARCH AND ENGINEERING JOURNALS 267

 © JUL 2021 | IRE Journals | Volume 5 Issue 1 | ISSN: 2456-8880

4.1 LoginPage REFERENCES

[1] G.Daniel, J. Cabot, L. Deruelle, and M. Derras,

‘‘Multi-platform chat-bot modeling and
deployment with the jarvis framework,’’ in
Advanced Information Systems Engineering
(Lecture Notes in Computer Science), vol.
11483, P. Giorgini and B. Weber, Eds. Rome,
Italy: Springer, Jun. 2019, pp. 177–193, doi:
10.1007/978-3-030- 21290-2_12.
[2] O. Diaz and F. M. Villoria, ‘‘Generating blogs
V. CONCLUSION & FUTURE out of product catalogues: An MDE approach,’’
ENHANCEMENT J. Syst. Softw., vol. 83, no. 10, pp. 1970–1982,
Oct. 2010, doi: 10.1016/j.jss.2010.05.075.
5.1 CONCLUSION [3] D. Falessi, N. Juristo, C. Wohlin, B. Turhan, J.
This study is a step further to improve the Münch, A. Jedlitschka, and M. Oivo, ‘‘Empirical
sustainability of car sharing as an environmental software engineering experts on the use of
friendly transportation service, thus contributing to students and professionals in experiments,’’
sustainability within our society. Empir Softw. Eng, vol. 23, no. 1, pp. 452–489,
Feb. 2018, doi: 10.1007/s10664-017-9523-3.
Moreover, our study provides a valuable method for [4] J.Hutchinson, J. Whittle, and M. Rouncefield,
practitioners. They can generate more data to “stress- ‘‘Model-driven engineering practices in
test” their system via simulation. This could be helpful industry: Social, organizational and managerial
to prepare for events (e.g., trade fairs), where a higher factors that lead to success or failure,’’ Sci.
vehicle demand is anticipated. Comput. Program., vol. 89, pp. 144–161, Sep.
2014.
5.2 FUTURE ENHANCEMENT
[5] P.Jackson and I. Moulinier, Natural Language
This work presents a research agenda based on
Processing for Online Applications: Text
interviews with experts in the field in order to guide
Retrieval, Extraction and Categorization, vol. 5.
future work from an industrial viewpoint, as current
Amsterdam, The Netherlands: John Benjamins,
agenda-setting contributions fail to include this
2007
perspective. Also, we derived guidelines based on
expert interviews to provide insights for companies [6] D.Kavaler, S. Sirovica, V. Hellendoorn, R.
seeking to implement chat-bots in customer care. Aranovich, and V. Filkov, ‘‘Perceived language
complexity in GitHub issue discussions and their
To explore, our expert panel and literature review effect on issue resolution,’’ in Proc. 32nd
showed us that there is a broad consensus that IEEE/ACM Int. Conf. Automated Softw. Eng.
intelligent chat-bots bare great potential for creating (ASE), Oct. 2017, pp.
value for companies in customer care. While we see [7] A.Kleppe, Software Language Engineering:
the existing research as highly important, our literature Creating Domain-Specific Language Using
review also indicates that the industrial perspective Metamodels. London, U.K.: Pearson, 2008.
should be more strongly included in identifying [8] L. C. Klopfenstein, S. Delpriori, S. Malatini, and
needed research. In this way, practice-based A. Bogliolo, ‘‘The rise of bots: A survey of
requirements can provide insights that may not have conversational interfaces, patterns, and
been captured in scientific literature, and thus advance paradigms,’’ in Proc. Conf. Designing Interact.
the IS research discipline. Syst. (DIS), 2017, pp. 555–565.

IRE 1702863 ICONIC RESEARCH AND ENGINEERING JOURNALS 268